CN106503708A - A kind of slag-soil truck car plate rough localization method based on color space information - Google Patents
A kind of slag-soil truck car plate rough localization method based on color space information Download PDFInfo
- Publication number
- CN106503708A CN106503708A CN201610922828.1A CN201610922828A CN106503708A CN 106503708 A CN106503708 A CN 106503708A CN 201610922828 A CN201610922828 A CN 201610922828A CN 106503708 A CN106503708 A CN 106503708A
- Authority
- CN
- China
- Prior art keywords
- car plate
- column
- row
- yellow
- color space
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/62—Text, e.g. of license plates, overlay texts or captions on TV images
- G06V20/63—Scene text, e.g. street names
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/56—Extraction of image or video features relating to colour
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/62—Text, e.g. of license plates, overlay texts or captions on TV images
- G06V20/625—License plates
Abstract
The invention discloses a kind of slag-soil truck car plate rough localization method based on color space information, including：The RGB color image of collection is transformed into hsv color space, according to yellow H, S, V passage codomain, the number of scan statistics yellow pixel line by line, floor projection and upright projection are carried out respectively, determine the initial termination row of car plate and initial end column, so as to find out the effective coverage of car plate；When the starting for inquiring about car plate terminates row or column, pixel count most row or column is first searched after floor projection or upright projection, then start progressively to search to both sides from the row or column, till yellow pixel number is unsatisfactory for condition i.e. yellow pixel number less than a, thus just can determine that the initial row or column of car plate and terminate row or column.The present invention realizes car plate fast rough by searching for the distributed intelligence of yellow pixel, and the pseudo- license plate area being prevented effectively from framing, its universality are higher.
Description
Technical field
The present invention relates to a kind of slag-soil truck car plate rough localization method based on color space information.
Background technology
Car license recognition (License Plate Recognition, LPR) is one kind typical case of computer image recognition technology
Application, it based on the technology such as Digital Image Processing, pattern recognition, computer vision, by the license plate in motion from multiple
Extract in miscellaneous background and identify, it is the important component part of intelligent transportation system, has been widely used in automatic charging
Stand, intelligent parking lot, vehicle flowrate monitoring, prohibited security zone management etc. place.
LPR systems mainly include License Plate, slant correction, Character segmentation, four parts of character recognition, Chinese scholars
Substantial amounts of research is carried out around this four processes, and has achieved numerous achievements in research.License Plate is that LPR systems are accurately identified
Premise, current license plate locating method mainly may be summarized to be two big class：One class is the textural characteristics based on gray scale domain, using car
Geological information of the Gray Level Jump of board priori, character and background and morphology connected domain etc. realizes License Plate, but should
Method is higher to image quality requirements, easily causes pseudo- license plate area, and the phase of varying environment during Image semantic classification
Pass threshold parameter setting is also difficult to unification causes its universality relatively low；Another kind of be based on color space information, using car plate with
The color of vehicle body is different, with reference to car plate priori, the information distribution of searching target color simultaneously realizes that License Plate, the method are fitted
For the License Plate of specific vehicle, but it is difficult to prove effective when the color of vehicle body or surrounding enviroment is close with car plate color.
Content of the invention
The technical problem to be solved in the present invention is the defect for overcoming prior art, there is provided a kind of based on color space information
Slag-soil truck car plate rough localization method, which has higher discrimination and positional accuracy, and universality is higher.
In order to solve above-mentioned technical problem, the invention provides following technical scheme：
A kind of slag-soil truck car plate rough localization method based on color space information of the present invention, which comprises the following steps：
S11, the RGB color image of collection is transformed into hsv color space, according to yellow H, S, V passage codomain, by
Row scans by column the number of statistics yellow pixel, carries out floor projection and upright projection respectively, determines the starting-termination row of car plate
With starting-end column, so as to find out the effective coverage of car plate；Wherein, yellow is distinguished in the value of each passage in hsv color space
For：H(0.1-0.3)、S(0.5-1.0)、V(0.35-1.0)；
S12, when inquire about car plate starting-termination row or column when, first search pixel count most after floor projection or upright projection
Many row or column, then start progressively to search to both sides from the row or column, until yellow pixel number is unsatisfactory for condition i.e. yellow picture
Prime number less than the initial row or column that till a, thus just can determine that car plate and terminates row or column；Wherein a is 2～5 natural number.
Further, in step s 12, when first time search terminate after, tentative step out b pixel to both sides, then
Search whether yellow pixel number meets condition, so circulation is till yellow pixel is unsatisfactory for condition；Wherein b is oneself of 4～8
So count.
The beneficial effect that reached of the present invention is：
The present invention is difficult to problem for slag-soil truck work under bad environment (such as car plate gets rusty or sludge is blocked), it is considered to
Slag-soil truck car plate feature, using the suitable license plate locating method based on color space information, by searching for dividing for yellow pixel
Cloth information realization car plate fast rough, the pseudo- license plate area being prevented effectively from framing, its universality are higher；When vehicle body or
The color of surrounding enviroment also has higher Position location accuracy with car plate color when close.
Specific embodiment
Hereinafter the preferred embodiments of the present invention are illustrated, it will be appreciated that preferred embodiment described herein is only used
In the description and interpretation present invention, it is not intended to limit the present invention.
A kind of slag-soil truck car plate rough localization method based on color space information, which comprises the following steps：
S11, the RGB color image of collection is transformed into hsv color space, according to yellow H, S, V passage codomain, by
Row scans by column the number of statistics yellow pixel, carries out floor projection and upright projection respectively, determines the starting-termination row of car plate
With starting-end column, so as to find out the effective coverage of car plate；
S12, when inquire about car plate starting-termination row (column) when, first search pixel count most after floor projection (upright projection)
Many row (column), then start progressively to search to both sides from the row (column), until yellow pixel number is unsatisfactory for condition (yellow pixel
Till number is less than a), thus just can determine that the initial row (column) of car plate and terminate row (column)；But, sometimes because car plate gets rusty
Or sludge the reason such as blocks and causes car plate yellow phenomenon of rupture, pseudo- starting row (column) at this moment occurs and pseudo- terminates row (column).For
Avoid the occurrence of pseudo- starting row (column) and pseudo- terminate row (column), after first time searches to be terminated, tentative step out b to both sides
Pixel, then search whether yellow pixel number meets condition, so circulation is till yellow pixel is unsatisfactory for condition.
Wherein parameter a, b is empirical value, and a typically takes that 2-5 is proper, and b typically takes 4-8 and compares conjunction.
Present invention identification to as if slag-soil truck characters on license plate, car plate is yellow bottom surplus.Body color is typically with car plate
Color different, therefore select the positioning mode based on color space information, for slag-soil truck of the minority vehicle body for yellow adopts other
Method is positioned.
The present invention is difficult to problem for slag-soil truck work under bad environment (such as car plate gets rusty or sludge is blocked), it is considered to
Slag-soil truck car plate feature, using the suitable license plate locating method based on color space information, by searching for dividing for yellow pixel
Cloth information realization car plate fast rough, the pseudo- license plate area being prevented effectively from framing, its universality are higher；When vehicle body or
The color of surrounding enviroment also has higher Position location accuracy with car plate color when close.
Finally it should be noted that：The preferred embodiments of the present invention are the foregoing is only, the present invention is not limited to,
Although being described in detail to the present invention with reference to the foregoing embodiments, for a person skilled in the art, which still may be used
To modify to the technical scheme described in foregoing embodiments, or equivalent is carried out to which part technical characteristic.
All any modification, equivalent substitution and improvements that within the spirit and principles in the present invention, is made etc., should be included in the present invention's
Within protection domain.
Claims (2)
1. a kind of slag-soil truck car plate rough localization method based on color space information, it is characterised in that comprise the following steps：
S11, the RGB color image of collection is transformed into hsv color space, according to yellow H, S, V passage codomain, line by line by
Column scan counts the number of yellow pixel, carries out floor projection and upright projection respectively, determines the starting-termination row of car plate and rises
Beginning-end column, so that find out the effective coverage of car plate；Wherein, yellow is respectively in the value of each passage in hsv color space：H
(0.1-0.3)、S(0.5-1.0)、V(0.35-1.0)；
S12, when inquire about car plate starting-termination row or column when, first search pixel count after floor projection or upright projection most
Row or column, then starts progressively to search to both sides from the row or column, until yellow pixel number is unsatisfactory for condition i.e. yellow pixel number
Less than the initial row or column and termination row or column that till a, thus just can determine that car plate；Wherein a is 2～5 natural number.
2. the slag-soil truck car plate rough localization method based on color space information according to claim 1, it is characterised in that
In step S12, after first time searches to be terminated, tentative step out b pixel to both sides, then search whether yellow pixel number expires
Sufficient condition, so circulation is till yellow pixel is unsatisfactory for condition；Wherein b is 4～8 natural number.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610922828.1A CN106503708A (en) | 2016-10-20 | 2016-10-20 | A kind of slag-soil truck car plate rough localization method based on color space information |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610922828.1A CN106503708A (en) | 2016-10-20 | 2016-10-20 | A kind of slag-soil truck car plate rough localization method based on color space information |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106503708A true CN106503708A (en) | 2017-03-15 |
Family
ID=58318492
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610922828.1A Pending CN106503708A (en) | 2016-10-20 | 2016-10-20 | A kind of slag-soil truck car plate rough localization method based on color space information |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106503708A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101398894A (en) * | 2008-06-17 | 2009-04-01 | 浙江师范大学 | Automobile license plate automatic recognition method and implementing device thereof |
| CN102375982A (en) * | 2011-10-18 | 2012-03-14 | 华中科技大学 | Multi-character characteristic fused license plate positioning method |
| CN101877126B (en) * | 2009-11-19 | 2012-12-19 | 东软集团股份有限公司 | Method and device for splitting license plate candidate area |
| CN103488978A (en) * | 2013-09-26 | 2014-01-01 | 浙江工业大学 | License plate location method based on gray level jump and character projection interval mode |
| CN104268509A (en) * | 2014-09-17 | 2015-01-07 | 深圳市捷顺科技实业股份有限公司 | Method and system for detecting license plate of dump truck |
| CN105488797A (en) * | 2015-11-25 | 2016-04-13 | 安徽创世科技有限公司 | License plate location method for HSV space |
-
2016
- 2016-10-20 CN CN201610922828.1A patent/CN106503708A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101398894A (en) * | 2008-06-17 | 2009-04-01 | 浙江师范大学 | Automobile license plate automatic recognition method and implementing device thereof |
| CN101877126B (en) * | 2009-11-19 | 2012-12-19 | 东软集团股份有限公司 | Method and device for splitting license plate candidate area |
| CN102375982A (en) * | 2011-10-18 | 2012-03-14 | 华中科技大学 | Multi-character characteristic fused license plate positioning method |
| CN103488978A (en) * | 2013-09-26 | 2014-01-01 | 浙江工业大学 | License plate location method based on gray level jump and character projection interval mode |
| CN104268509A (en) * | 2014-09-17 | 2015-01-07 | 深圳市捷顺科技实业股份有限公司 | Method and system for detecting license plate of dump truck |
| CN105488797A (en) * | 2015-11-25 | 2016-04-13 | 安徽创世科技有限公司 | License plate location method for HSV space |
Non-Patent Citations (7)
| Title |
|---|
| GANG LI 等: "A Yellow License Plate Location Method Based on RGB Model of Color Image and Texture of Plate", 《SECOND WORKSHOP ON DIGITAL MEDIA AND ITS APPLICATION IN MUSEUM & HERITAGE》 * |
| LIN LUO 等: "An Efficient Method of License Plate Location", 《THE 1ST INTERNATIONAL CONFERENCE ON INFORMATION SCIENCE AND ENGINEERING (ICISE2009)》 * |
| 王夏黎 等: "一种基于HSV颜色空间的车辆牌照提取方法", 《计算机工程》 * |
| 王洪建: "基于HSV颜色空间的一种车牌定位和分割方法", 《仪器仪表学报》 * |
| 甄荣 等: "一种新的基于颜色的车牌定位方法", 《第二届全国智能视觉监控学术会议论文集》 * |
| 薛征: "车牌识别系统关键技术的研究", 《中国优秀硕士学位论文全文数据库信息科技辑》 * |
| 陈帅 等: "基于HSV空间的创新型车牌定位方法", 《北京建筑大学学报》 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106951879B (en) | Multi-feature fusion vehicle detection method based on camera and millimeter wave radar | |
| CN110660254B (en) | Traffic signal lamp detection and intelligent driving method and device, vehicle and electronic equipment | |
| CN103116751B (en) | A kind of Method of Automatic Recognition for Character of Lcecse Plate | |
| Deng et al. | Double lane line edge detection method based on constraint conditions hough transform | |
| CN101872416B (en) | Vehicle license plate recognition method and system of road image | |
| CN109726717B (en) | Vehicle comprehensive information detection system | |
| CN107729899A (en) | A kind of number-plate number recognition methods and device | |
| CN107665599A (en) | The parking position automatic identifying method of view-based access control model detection | |
| CN107016362B (en) | Vehicle weight recognition method and system based on vehicle front windshield pasted mark | |
| CN107180230B (en) | Universal license plate recognition method | |
| CN106529534A (en) | Variable-length license plate character segmentation method based on hybrid tilt correction and projection method | |
| Youjin et al. | A robust lane detection method based on vanishing point estimation | |
| CN103544480A (en) | Vehicle color recognition method | |
| CN103903282A (en) | Target tracking method based on LabVIEW | |
| Liu et al. | ROI perspective transform based road marking detection and recognition | |
| CN106503709A (en) | A kind of slag-soil truck characters on license plate intelligent identification Method | |
| Lin et al. | Adaptive IPM-based lane filtering for night forward vehicle detection | |
| CN104182728A (en) | Vehicle logo automatic location and recognition method based on pattern recognition | |
| CN105117724A (en) | License plate positioning method and apparatus | |
| CN106022268A (en) | Identification method and device of speed limiting sign | |
| Chen et al. | Real-time vision-based multiple vehicle detection and tracking for nighttime traffic surveillance | |
| Xu et al. | Study on a robust approach of lane departure warning algrithm | |
| Liu et al. | A novel multi-oriented chinese text extraction approach from videos | |
| Zhao et al. | Research and implementation of license plate recognition technology | |
| Skodras et al. | Rear lights vehicle detection for collision avoidance |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170315 |
|
| RJ01 | Rejection of invention patent application after publication |